Machine Learning-Based Intelligent Scoring System for English Essays under the Background of Modern Information Technology

Table 2

The general idea to score essays.

Order	Step
1	The method and TextRank method are used to select typical labels to score essays
2	With general feature vector to represent the essay to be scored and the essay in the data set, their feature vectors are compared for cosine similarity. Then, the k value of the kNN algorithm model is evaluated, and typical comment tags of essays with high similarity to the essay to be scored are screened to eliminate the duplicates to form the score.
3	To get the score of the essay, it is necessary to use the method to calculate the weight of word segments and arrange them in descending order. Then, the sequence of word segments is obtained. represents the result of by TF method, and is the result by method, as follows: .
4	The TextRank method is used to estimate the weight value of each word segment, and the word segment sequence is obtained in descending order. is a given value, expressed as follows. represents the position in the sequence, represents the position in the sequence, and takes the intersection of the two values to obtain the comprehensive scoring sequence of all essays
5	In the scoring process, essay to be scored and that in the data set are expressed as and